PentestLLM
API providing 367 security-tuned and uncensored models for authorized penetration testing, red teaming and bug bounty work, with pricing from $10 prepaid
API providing 367 security-tuned and uncensored models for authorized penetration testing, red teaming and bug bounty work, with pricing from $10 prepaid
The pitch

PentestLLM is an API gateway offering 367 security-tuned, abliterated and uncensored large language models designed for authorized penetration testing, red team exercises, bug bounty hunting and CTF competitions. The service provides access to these models through a single prepaid API key using the OpenAI SDK format, with token-based pricing starting from $10 top-ups that never expire. Beyond chat, the platform includes agent tools for web search and code execution, PDF document reading, automatic routing between model tiers, response caching for extended conversations, session logging, and specialized endpoints for embeddings and batch processing. Models are daily-checked for authenticity and can be used with existing security tools like Burp Suite, Nuclei and Metasploit, supporting use cases including recon automation, proof-of-concept drafting and report generation.
Under the hood
- 367 security-tuned and uncensored chat models
- Agent tools: web search, code sandbox, remote MCP servers
- PDF file reading and document processing
- Response caching for 1/10 cost on repeated requests
- Embeddings, speech-to-text and batch processing
- Daily model authentication check
- Web search tool at $0.01 per search
- OpenAI and Anthropic API format compatibility
Pricing
Pricing model: Paid
Prepaid plans: Plus $10/month ($20 usage), Pro $25/month ($50 usage), Max $100/month ($200 usage), Ultra $250/month ($500 usage). Pay-as-you-go: top up from $10 USD with no subscription. Per-token pricing: output from $0.08 to over $1 per million tokens depending on model. Bonus credit: 5% from $200
Quick answers
Who is PentestLLM for?
Penetration testers, red teams, bug bounty hunters and CTF players doing authorized work on systems you own or have written permission to test. The key is sold under the acceptable use policy.
Does it work with Burp Suite, Nuclei, Metasploit or Kali?
Yes, it works alongside these tools. The model reads the output those tools already produced, ranks findings, reviews code and drafts reports; your tools and your judgement decide what runs. On Kali it runs in terminal agents and MCP clients through a base URL and key.
Can I try the models before topping up?
Yes. The playground gives a few capped turns a day on free-turn models with no sign-up. A free account adds 10 console messages a day on glm-5.3-flash-uncensored, and a key runs every model per token.
What does abliterated mean?
An abliterated model is an open-weight model whose refusal direction has been removed from the weights, so it answers instead of declining. It is not a jailbreak prompt.
What is the lowest output price?
Gemma 3n E2B (Uncensored) has the lowest output price at $0.08 per million tokens as of the catalog date.
PentestLLM has a free listing. The owner can unlock the full profile with a paid launch for $5:
- Founder story (locked)
- Milestones (locked)
- Demo video (locked)
- Dofollow website link: not on this free listing (its website link is nofollow)